VSTE
Littera Scripta

ISSN (online): 1805-9112

Open access

Evaluation of Performance of MLP Neural Networks and RBF Neural Networks in Adjusting Time Series of the Development of the Trade Balance Between the USA and the PRC

Jaromír Vrbka1*, Petr Šuleř1, Veronika Machová1, Jakub Horák1

  1. Institute of Technology and Business, School of Expertness and Valuation, České Budějovice, Czechia

* Corresponding author: vrbka@mail.vstecb.cz

Abstract

Artificial neural networks are widely used for predicting values, for solving possible future problems and are able to provide various solutions in problem estimation, regression or optimisation. They are useful for predicting time series too. The aim of the paper is to analyse and evaluate the performance of multilayer neural networks (hereinafter referred to as "MLP") and neural networks of radial basis function (hereinafter referred to as "RBF) in adjusting time series on the example of the trade balance between the United States and the People's Republic of China. Regression was performed using neural structures. We generated multilayer perceptron networks and neural networks of radial basis function and we generated two sets of artificial neural networks. Time was the continuous independent variable. We determined the trade balance of the USA and the PRC as a dependent variable. We can state that due to the great simplification of reality, it is not possible to predict the emergence of extraordinary situations and their impact on the trade balance of the USA and the PRC. We can state that when an adjusted time series is derived from a single variable, time, RBFs perform better than MLPs. In order to make the prediction more accurate and its calculation easier, it seems appropriate to use RBF networks, which brings a relatively high degree of accuracy.

Keywords:multilayer neural networksRBFtrade balancefuture development predictionUSAPeople’s Republic of Chinacorrelation coefficient

References

  1. Fajardo-Toro, C. H., Cobo, L. A., & Martínez-Sánchez, P. M. T. (2019). Comparison of the behavior of recurrent neural networks against other methods to obtain time series forecasts. RISTI - Revista Ibérica de Sistemas e Tecnologias de Informação, E17, 1022–1034.
  2. Chang, T. S. (2011). A comparative study of artificial neural networks and decision trees for digital game content stocks price prediction. Expert Systems with Applications, 38(12), 14846–14851.
  3. Klieštik, T. (2013). Models of autoregression conditional heteroscedasticity GARCH and ARCH as a tool for modeling the volatility of financial time series. Ekonomicko-Manažérske Spektrum, 7(1), 2–10.
  4. Liu, Z., et al. (2009). Modelling and prediction of the CNY exchange rate using RBF neural network. In 2009 International Conference on Business Intelligence and Financial Engineering (pp. 38–41).
  5. Machová, V., & Vochozka, M. (2019). Using artificial intelligence in analyzing and predicting the development of stock prices of a subject company. In Sustainable Growth and Development of Economic Systems (pp. 235–245). Springer International Publishing.
  6. Magni, C. A. (2005). On decomposing net final values: EVA, SVA and shadow project. Theory and Decision, 59(1), 51–95.
  7. Rodrigues, F., Markou, I., & Pereira, F. C. (2019). Combining time-series and textual data for taxi demand prediction in event areas: A deep learning approach. Information Fusion, 49, 120–129.
  8. Rowland, Z., Šuleř, P., & Vochozka, M. (2019). Comparison of neural networks and regression time series in estimating the Czech Republic and China trade balance. SHS Web of Conferences, 61.
  9. Vochozka, M. (2017a). Effect of the economic outturn on the cost of debt of an industrial enterprise. SHS Web of Conferences, 39.
  10. Vochozka, M. (2017b). Inventory management using artificial neural networks in a concrete case. In Proceedings of the 5th International Conference Innovation Management, Entrepreneurship and Sustainability (IMES 2017).
  11. Vochozka, M., & Sheng, P. (2016). The application of artificial neural networks on the prediction of the future financial development of transport companies. Communications - Scientific Letters of the University of Žilina, 18(2), 62–67.
  12. Vochozka, M. (2010). Vývoj metod komplexního hodnocení výkonnosti podniku [Development of methods for comprehensive evaluation of company performance]. Politická Ekonomie, 58(5), 675–688.
  13. Vrbka, J., Rowland, Z., & Šuleř, P. (2019). Comparison of neural networks and regression time series in estimating the development of the EU and the PRC trade balance. SHS Web of Conferences, 61.
  14. Vrbka, J., et al. (2019). Considering seasonal fluctuations in equalizing time series by means of artificial neural networks for predicting development of USA and People’s Republic of China trade balance. Littera Scripta, 12(2), 178–193.
  15. Wedding, D. K., & Cios, K. J. (1996). Time series forecasting by combining RBF networks, certainty factors, and the Box-Jenkins model. Neurocomputing, 10(2), 149–168.
  16. Zhang, G. P., Cebeci, A. F., & Imamoglu, S. Z. (2001). An investigation of neural networks for linear time-series forecasting. Computational Economics, 28(12), 1183–1202.